AI ALIGNMENT FORUM
AF

Wikitags

Machine Learning (ML)

Edited by John_Maxwell, pedrochaves, et al. last updated 30th Dec 2024

Machine Learning is a general field of study that deals with automated statistical learning and pattern detection by non-biological systems. It can be seen as a sub-domain of artificial intelligence that specifically deals with modeling and prediction through the knowledge extracted from training data. As a multi-disciplinary area, it has borrowed concepts and ideas from other areas like pure mathematics and cognitive science.

Understanding different machine learning algorithms

The most widely used distinction is between unsupervised (e.g. k-means clustering, principal component analysis) vs supervised (e.g. Support Vector Machines, logistic regression) methods. The first approach identifies interesting patterns (e.g. clusters and latent dimensions) in unlabeled training data, whereas the second takes labeled training data and tries to predict the label for unlabeled data points from the same distribution.

Another important distinction relates to the bias/variance tradeoff -- some machine learning methods are capable of recognizing more complex patterns, but the tradeoff is that these methods can overfit and generalize poorly if there's noise in the training data -- especially if there's not much training data available.

There are also subfields of machine learning devoted to operating on specific kinds of data. For example, Hidden Markov Models and recurrent neural networks operate on time series data. Convolutional neural networks are commonly applied to image data.

Applications

The use of machine learning has been widespread since its formal definition in the 50’s. The ability to make predictions based on data has been extensively used in areas such as analysis of financial markets, natural language processing and even brain-computer interfaces. Amazon’s product suggestion system makes use of training data in the form of past customer purchases in order to predict what customers might want to buy in the future.

In addition to its practical usefulness, machine learning has also offered insight into human cognitive organization. It seems likely machine learning will play an important role in the development of artificial general intelligence.

Further Reading & References

  • The Elements of Statistical Learning

See Also

  • Prediction
Subscribe
3
Subscribe
3
Discussion0
Discussion0
Posts tagged Machine Learning (ML)
31Paper: Discovering novel algorithms with AlphaTensor [Deepmind]
LawrenceC
3y
11
51A Bird's Eye View of the ML Field [Pragmatic AI Safety #2]
Dan H, TW123
3y
2
64EfficientZero: How It Works
1a3orn
4y
2
47Matt Botvinick on the spontaneous emergence of learning algorithms
Adam Scholl
5y
59
50the scaling “inconsistency”: openAI’s new insight
nostalgebraist
5y
8
21Using GPT-N to Solve Interpretability of Neural Networks: A Research Agenda
Logan Riggs, Gurkenglas
5y
0
22The No Free Lunch theorems and their Razor
Adrià Garriga-alonso
3y
0
50Self-fulfilling misalignment data might be poisoning our AI models
TurnTrout
6mo
13
41Revealing Intentionality In Language Models Through AdaVAE Guided Sampling
jdp
2y
0
29Unsolved ML Safety Problems
jsteinhardt
4y
0
97chinchilla's wild implications
nostalgebraist
3y
13
106A Mechanistic Interpretability Analysis of Grokking
Neel Nanda, Tom Lieberum
3y
18
76DeepMind: Generally capable agents emerge from open-ended play
Daniel Kokotajlo
4y
11
71New Scaling Laws for Large Language Models
1a3orn
3y
1
78interpreting GPT: the logit lens
nostalgebraist
5y
14
Load More (15/136)
Add Posts